kaixinbear / CAPE

(CVPR2023) CAPE: Camera View Position Embedding for Multi-View 3D Object Detection

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

mAP is 0

shadow2469 opened this issue · comments

I followed your project configuration, and when I train the cape_r50_1408x512_24ep_wocbgs_imagenet_pretrain.py file, the mAP is always 0.

commented

I have also encountered the same problem. I followed the steps in the README.md and trained using the provided dataset and pretrain model, but the results I obtained were very strange.

Can you provide your training log ?